GCPO

Official code for “Goal-Conditioned On-Policy Reinforcement Learning” (NeurIPS 2024).

code

1. code for velocity vector control of Fixed-wing UAVs.
2. code for PointMaze.
3. code for Reach.

Citation

@inproceedings{gong2024goal,
  title={Goal-Conditioned On-Policy Reinforcement Learning},
  author={Xudong, Gong and Dawei, Feng and Kele, Xu and Bo, Ding and Huaimin, Wang},
  booktitle={Conference on Neural Information Processing Systems},
  year={2024},
}